Advertisement

Local Discriminant Regions Using Support Vector Machines for Object Recognition

  • David Guillamet
  • Jordi Vitriá
Conference paper
First Online:
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1876)

Abstract

Visual object recognition is a difficult task when we consider non controlled environments. In order to manage problems like scale, viewing point or occlusions, local representations of objects have been proposed in the literature. In this paper, we develop a novel approach to automatically choose which samples are the most discriminant ones among all the possible local windows of a set of objects. The use of Support Vector Machines for this task have allowed the management of high dimensional data in a robust and founded way. Our approach is tested on a real problem: the recognition of informative panels.

Keywords

Support Vector Machines Local Appearance Computer Vision Object Recognition 
Download to read the full conference paper text

References

  1. 1.
    M. Black and A. Jepson. Eigentracking: Robust and tracking of articulated objects using a view-based representation. In Proc. of 4th European Conference on Computer Vision, volume 1, pages 329–342, Cambridge, April 1996.Google Scholar
  2. 2.
    V. Cherkassky and F. Mulier. Learning From Data. Wiley-Interscience, New York, 1998.zbMATHGoogle Scholar
  3. 3.
    V. C. de Verdière and J. L. Crowley. Visual recognition using local appearance. In Proc. ECCV’98, 1998.Google Scholar
  4. 4.
    W. Grimson. Object Recognition by Computer. MIT Press, 1990.Google Scholar
  5. 5.
    P. J. B. Hancock, R. J. Baddeley, and L. S. Smith. The principal components of natural images. Neural Networks, 3:61–70, 1992.CrossRefGoogle Scholar
  6. 6.
    D. Huttenlocher and S. Ullman. Recognizing solid objects by alignement. In Proc. IEEE ICCV’87, pages 102–111, 1987.Google Scholar
  7. 7.
    D. G. Lowe. Three-dimensional object recognition from single two dimensional images. Artificial Intelligence, 31:355–395, 1987.CrossRefGoogle Scholar
  8. 8.
    H. Murase and S. Nayar. Learning and recognition of 3d objects from appearance. In Proc. IEEE Qualitative Vision Workshop, pages 39–49, 1993.Google Scholar
  9. 9.
    K. Ohba and K. Ikeuchi. Detectability, uniqueness and reliability of eigen windows for stable verification of partially occluded objects. IEEE Transaction on PAMI, 19(9):1043–1048, September 1997.Google Scholar
  10. 10.
    R. P. Rao. Dinamic Appearance-Based Vision. PhD thesis, University of Rochester, 1997.Google Scholar
  11. 11.
    B. Schiele and A. Pentland. Probabilistic object recognition and localization. Technical Report 499, MIT Media Laboratory, Perceptual Computing, 1999.Google Scholar
  12. 12.
    C. Schmid and R. Mohr. Combining greyvalue invariants with local constraints for object recognition. In Proc. IEEE CVPR’96, pages 872–877, 1996.Google Scholar
  13. 13.
    M. Turk and A. Pentland. Face recognition using eigenfaces. In Proc. of IEEE Conf. on CVPR’91, pages 586–591, June 1991.Google Scholar
  14. 14.
    V. Vapnik. The Nature of Statistical Learning Theory. Springer Verlag, New York, 1995.zbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • David Guillamet
    • 1
  • Jordi Vitriá
    • 1
  1. 1.Centre de Visió per Computador-Dept. InformàticaUniversitat Autònoma deBarcelonaBellaterraSpain

Personalised recommendations

Cite paper